nafyi.

PUBLIC VIEWPOINTS

Tibo Sottiaux

Interview participant ·

1 interviews · 3 viewpoints · 1 topics

Content updated:

Translations are for reading; original excerpts remain the evidence.

Viewpoints by topic

Attributed viewpoints, ordered by interview date. A snapshot of these conversations, not a definitive statement of someone’s beliefs.

AI products

View this topic
AI products

Research and product should be designed together

Tibo Sottiaux describes wanting to join a group where research and product were designed together and the relevant parameters were considered together.

Supporting evidence

Original excerpt

I wanted to join a group where all the parameters were considered together, where research and product were really co-designing.

Tibo Sottiaux·

Building Codex with Tibo Sottiaux

Additional context is not included in this excerpt. Read the original conversation.

Open original · 12:39 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 12:39.

Tibo Sottiaux
Share insight
AI products

Avoid elaborate workarounds for model limitations

Tibo Sottiaux describes principles centered on users, product coherence and the direction of model development. He cautions that a 10,000-line workaround for model flaws may mean the team is doing the wrong thing.

Supporting evidence

Original excerpt

care about the user, care about the coherence of the product, care about the models and where they're going. If you're doing something and you're building this 10,000 lines of code crutch to work around the model flaws, you're probably doing the wrong thing. So we have a set of principles, but it's just really So like a team culture and ethos at this point.

Tibo Sottiaux·

Building Codex with Tibo Sottiaux

Additional context is not included in this excerpt. Read the original conversation.

Open original · 42:23 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 42:23.

Tibo Sottiaux
Share insight
AI products

Security flags can block pull-request merges

Tibo Sottiaux says OpenAI benchmarks code-review models for correctness and security. He describes mandatory checks that block pull-request merges when a security issue is flagged.

Supporting evidence

Original excerpt

When we benchmark them, it's like they're superhuman in code review. And this is not just true for correctness. This is also true for security, for example, where they're capable of reasoning across Very, very complex things. And then coming up with, hey, you have a critical security vulnerability here, which is now mandatory across all of OpenAI pull requests. We block pull requests from merging if we flag them with a security issue.

Tibo Sottiaux·

Building Codex with Tibo Sottiaux

Additional context is not included in this excerpt. Read the original conversation.

Open original · 47:53 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 47:53.

Tibo Sottiaux
Share insight

Statements by interview date1

Statements are ordered by the original interview publication date; differences in wording do not establish a change of position.